Air–sea fluxes — the exchanges of heat, moisture, and gases between the ocean and atmosphere —play a key role in shaping weather and climate. Traditional models often treat these fluxes in a fixed, “one-size-fits-all” way, missing their natural variability. This LEAP study , led by Jiarong Wu, introduces a new probabilistic framework that uses neural networks and observational data to better capture both the average behavior and the uncertainty of these fluxes. The results show that accounting for this variability can influence ocean temperature and mixing, especially during spring, offering a promising step toward more realistic climate and weather simulations.